Skip to content

Nathan Lambert personal blog

Q* Hypothesis: Enhancing Reasoning, Rewards, and Synthetic Data

interconnects.ai published 2023-11-24

Emergency special: The information we need to understand what Q* is was right in front of us, but the memes are more fun than reality.

Read on interconnects.ai → Discuss on HN (63) Archived copy

Points: 107
HN comments: 63
Submissions: 1
Cited by: 0 commenters

AI & Machine Learning Math & Algorithms 2023

On Hacker News

Submitted	Title on HN	Points	Comments
Nov 24, 2023	Q* Hypothesis: Enhancing Reasoning, Rewards, and Synthetic Data by Jimmc414	107	63

More from Nathan Lambert

All 8 posts →

GLM-5.2 is a step change for open agents

2026367 points223 comments AI & Machine Learning details

The AI research job market

2023207 points183 comments AI & Machine Learning details

A look at Apple's technical approach to AI including core model performance etc.

2024196 points106 comments AI & Machine Learning details

GPT-4.5: "Not a frontier model"?

2025166 points161 comments AI & Machine Learning details

How RLHF Works

2023165 points32 comments AI & Machine Learning details

Open-source AI and open models reading list

2026162 points30 comments AI & Machine Learning details

Related posts from the same era

Bing: “I will not harm you unless you harm me first”

Simon Willison20233,363 points1,673 commentscited by 6 details

GPT-4o

OpenAI Blog20243,138 points2,366 commentscited by 16 details

Open source AI is the path forward

Meta Newsroom20242,360 points887 commentscited by 5 details

Building a Virtual Machine Inside ChatGPT

Jonas Degrave20222,029 points908 commentscited by 16 details

The man who killed Google Search?

Ed Zitron20241,884 points878 commentscited by 47 details

ChatGPT Plugins

OpenAI Blog20231,875 points1,106 commentscited by 14 details